CN115099029B - Method for calculating influence of cylinder efficiency change of supercritical thermal power generating unit on heat consumption rate - Google Patents
Method for calculating influence of cylinder efficiency change of supercritical thermal power generating unit on heat consumption rate Download PDFInfo
- Publication number
- CN115099029B CN115099029B CN202210706730.8A CN202210706730A CN115099029B CN 115099029 B CN115099029 B CN 115099029B CN 202210706730 A CN202210706730 A CN 202210706730A CN 115099029 B CN115099029 B CN 115099029B
- Authority
- CN
- China
- Prior art keywords
- pressure cylinder
- efficiency
- cylinder
- change
- influence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000013528 artificial neural network Methods 0.000 claims abstract description 33
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 21
- 238000012360 testing method Methods 0.000 claims abstract description 17
- 238000010606 normalization Methods 0.000 claims abstract description 6
- 238000000605 extraction Methods 0.000 claims description 27
- 238000010521 absorption reaction Methods 0.000 claims description 6
- 230000002519 immonomodulatory effect Effects 0.000 claims description 3
- 230000035772 mutation Effects 0.000 claims description 3
- 238000010248 power generation Methods 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 abstract description 19
- 238000004458 analytical method Methods 0.000 abstract description 6
- 238000003745 diagnosis Methods 0.000 abstract description 4
- 238000012932 thermodynamic analysis Methods 0.000 abstract description 3
- 230000000694 effects Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000001172 regenerating effect Effects 0.000 description 1
- 229920006395 saturated elastomer Polymers 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Geometry (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
Abstract
The invention discloses a calculation method for the influence of cylinder efficiency change of a supercritical thermal power unit on a heat consumption rate, which comprises the following steps: 1) Collecting test data; 2) Normalizing the collected test data; 3) According to the test data after normalization treatment, determining the efficiency eta of the high-pressure cylinder HP Efficiency eta of medium pressure cylinder IP And determining the efficiency eta of the low-pressure cylinder based on RBF neural network prediction algorithm LP The method comprises the steps of carrying out a first treatment on the surface of the 4) Respectively changing the efficiency eta of the high-pressure cylinder HP Efficiency eta of medium pressure cylinder IP And low pressure cylinder efficiency eta LP The efficiency of each cylinder is reduced by 1%; 5) And under the condition that the efficiency of each cylinder is reduced by 1%, obtaining a corresponding heat consumption rate, and comparing and analyzing to determine the influence of the heat efficiency change of each cylinder on the heat loss. The invention overcomes the complexity brought by the traditional thermodynamic analysis method and reduces the error in the analysis and diagnosis of the steam turbine thermal economy.
Description
Technical Field
The invention belongs to the field of thermal power unit performance analysis, and particularly relates to a calculation method for influence of supercritical thermal power unit cylinder efficiency change on heat consumption rate.
Background
According to the principle of the steam turbine, when the relative internal efficiency of the high-pressure cylinder of the steam turbine changes, the heat absorption capacity of cold re-steam in the reheater is changed, so that the ideal circulating heat efficiency of the steam turbine changes, the temperature of the hot re-steam is controlled by the boiler generally, and on the premise that the temperature of the re-hot steam is kept unchanged, the relative internal efficiency of the high-pressure cylinder, the relative internal efficiency of the low-pressure cylinder, the ideal heat drop and the reheat coefficient of the whole steam turbine are not influenced by the change of the relative internal efficiency of the high-pressure cylinder. When the relative internal efficiency of the medium pressure cylinder changes, the steam inlet parameter of the low pressure cylinder is changed, so that the expansion process curve of the low pressure cylinder changes correspondingly. It follows that the single cylinder efficiency variation of the turbine is not an isolated thermodynamic process.
Meanwhile, for a steam turbine with backheating extraction, when the relative internal efficiency of the cylinder body changes, parameters after each pressure stage change. If the resistance coefficient of the steam extraction pipeline of each corresponding heater is basically unchanged, the steam side saturation pressure corresponding to each heater and the saturated water enthalpy corresponding to each heater are also changed; under the condition of a certain main steam parameter, the heat absorption quantity of the steam in the superheater is changed, so that the ideal circulating heat efficiency of the steam turbine is changed. Thus, single cylinder efficiency variation is a complex thermodynamic process involving other cylinders and coupled to each other with the respective connected regenerator system.
At present, many scholars have studied the problem of calculating the enthalpy of steam turbine exhaust, and theoretical calculation methods include an energy balance method, a residual speed loss method, a curve iteration method, an entropy increase method, a BP neural network method and the like. Although these methods have their characteristics, the most limited method is to directly measure the humidity of the exhaust gas of the turbine. However, the development of the measuring device is still in a test stage. Therefore, under the existing condition, a new calculation method of the relative internal efficiency of the low-pressure cylinder of the steam turbine must be proposed to analyze the influence of the change of the efficiency of the steam turbine cylinder on the heat rate of the unit. The traditional analysis method of the influence of the cylinder efficiency on the heat consumption is complex, and the calculation accuracy is low, so that errors in analysis and diagnosis are often ignored.
Disclosure of Invention
The invention aims to provide a calculation method for the influence of the cylinder efficiency change of a supercritical thermal power unit on the heat consumption rate, so that the complexity brought by the traditional thermodynamic analysis method is overcome, and the error in the analysis and diagnosis of the thermal economy of a steam turbine is reduced.
In order to achieve the above purpose, the invention adopts the following technical scheme:
a calculation method for influence of cylinder efficiency change of a supercritical thermal power unit on heat consumption rate comprises the following steps:
1) Collecting test data;
2) Normalizing the collected test data;
3) According to the test data after normalization treatment, determining the efficiency eta of the high-pressure cylinder HP Efficiency eta of medium pressure cylinder IP And determining the efficiency eta of the low-pressure cylinder based on RBF neural network prediction algorithm LP ；
4) Respectively changing the efficiency eta of the high-pressure cylinder HP Efficiency eta of medium pressure cylinder IP And low pressure cylinder efficiency eta LP The efficiency of each cylinder is reduced by 1%;
5) And under the condition that the efficiency of each cylinder is reduced by 1%, obtaining a corresponding heat consumption rate, and comparing and analyzing to determine the influence of the heat efficiency change of each cylinder on the heat loss.
A further development of the invention is that in step 1), the test data comprise the temperature, pressure and flow rate of the individual test points.
In the step 3), the cylinder efficiency of the low-pressure cylinder is based on an RBF neural network prediction algorithm, and the 1-6 sections of steam extraction point models in a superheat region are firstly fitted by utilizing a 1 st layer RBF neural network to predict the steam extraction enthalpy of the 7 th section;
the predicted data and the input data of the 1 st layer are used as the input data of the 2 nd RBF neural network, and the 8 th section of steam extraction enthalpy is predicted;
and then, the predicted data and the input data of the 2 nd layer are used as the input data of the 3 rd layer RBF neural network, and the final steam exhaust enthalpy is predicted, so that the cylinder efficiency of the low-pressure cylinder of the steam turbine is calculated.
The invention further improves that the RBF neural network prediction algorithm comprises the following calculation steps:
(1) Determining the number of nodes of the input layer and the output layer according to the problem to form a central set sample;
(2) Randomly selecting a predetermined number of samples from the central set, wherein the corresponding input vector is used as the center of the hidden layer unit, and the number of the selected samples is used as the number of the hidden layer unit, so that an initial population is randomly generated;
(3) Evolution operations, including mutation and crossover operator operations;
(4) Firstly constructing a hidden layer structure of a network by using a selected sample, determining weights from the hidden layer to an output layer by using a gradient method, calculating total errors of the network, and executing the step (3) if the total errors of the network do not reach the maximum network structure which is originally set, otherwise, executing the step (5);
(5) The fitness of each antibody was calculated and the fitness function was taken as:
wherein: c is a constant; e, e i Is an iteration error; f (i) is an fitness function;
(6) Performing concentration-based immunomodulation on the antibodies, generating new individuals, and transferring to step (3); wherein, the larger the antibody fitness is, the larger the selection probability is; the greater the antibody concentration, the less the probability of selection; the phenomenon of immature convergence can be improved by further ensuring the diversity of the antibody while retaining the antibody with high adaptability.
The invention is further improved in that the influence of the high-pressure cylinder efficiency change on the heat consumption is deduced, the high-pressure cylinder efficiency change causes the internal power change of the high-pressure cylinder and the heat absorption capacity change of the boiler reheater, and the high-pressure cylinder efficiency change causes the vapor discharge enthalpy change quantity of the high-pressure cylinder to be calculated by the following formula:
wherein: δh HPE Is the change quantity of the exhaust enthalpy of the high-pressure cylinder, kJ/kg; h is a HPE And h' HPE The enthalpy of exhaust gas of the high-pressure cylinder before and after the change is kJ/kg; Δη HP And eta HP The absolute value of the high-pressure cylinder efficiency change and the high-pressure cylinder efficiency are respectively;
wherein: g RH Kg/s is the reheat flow of the boiler; r is R HP The nominal internal power of the high-pressure cylinder accounts for the percentage of the total power generation power, q is the heat consumption rate of the turbine, kJ/(kW.s); Δq is the variation of the heat rate of the steam turbine, kJ/(kW.s); kJ/s; p is the generated power, kW.
The invention is further improved in that the definition formula of the heat consumption rate q of the steam turbine is as follows:
wherein: q is the heat quantity, kJ/s.
The invention is further improved in that the influence of the medium pressure cylinder efficiency change on the heat consumption rate is deduced, and the medium pressure cylinder efficiency change leads to the inner power change of the medium pressure cylinder on one hand and affects the inner power change of the low pressure cylinder on the other hand; the medium pressure cylinder efficiency variation is calculated using the following formula:
wherein: r is R IP The nominal internal power of the medium-pressure cylinder accounts for the percentage of the total generated power; LF is dissipation factor;
the loss factor LF is actually the loss proportion caused by the fact that the enthalpy increase such as the steam inlet of the low-pressure cylinder is not effectively utilized, and the loss factor (1-LF) is the proportion effectively utilized; r is R IP Nominal power for the medium pressure cylinder as a percentage of total power.
The invention is further improved in that the influence of the change of the efficiency of the low pressure cylinder on the heat consumption rate is deduced, and the influence of the change of the efficiency of the low pressure cylinder on the heat consumption rate is as follows:
compared with the prior art, the invention has at least the following beneficial technical effects:
the invention provides a calculation method of the influence of the cylinder efficiency change of a supercritical thermal power unit on the heat consumption rate, which is based on a radial basis function network (RBF neural network) algorithm, adopts a prediction model to determine the efficiency of a low-pressure cylinder, adopts the prediction model, and predicts the extraction enthalpy of a 7 th section by fitting a 1-6 section extraction point model in a superheat region by utilizing a 1 st layer RBF network; the predicted data and the input data of the 1 st layer are used as the input data of the 2 nd RBF neural network, and the 8 th section of steam extraction enthalpy is predicted; and then, the predicted data and the input data of the layer 2 are used as the input data of the RBF neural network of the layer 3, and the final steam exhaust enthalpy is predicted. The method analyzes the influence of the efficiency of the high pressure cylinder, the medium pressure cylinder and the low pressure cylinder on the heat consumption rate by 1 percent, solves the defect that the exhaust enthalpy of the traditional low pressure cylinder cannot be directly determined compared with the traditional technology, overcomes the complexity brought by the traditional thermodynamic analysis method, and reduces the error in the analysis and diagnosis of the heat economy of the steam turbine.
Drawings
FIG. 1 is a schematic illustration of a radial basis function network (RBF neural network prediction algorithm) model of an embodiment of the present invention;
FIG. 2 is a schematic flow chart of an embodiment of the invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
The invention provides a calculation method for the influence of cylinder efficiency change of a supercritical thermal power unit on heat consumption rate, which is used for determining low-pressure cylinder efficiency based on a radial basis function network (RBF neural network prediction algorithm) algorithm and determining high-pressure cylinder efficiency and medium-pressure cylinder efficiency according to collected data; further, deriving a correlation between each cylinder efficiency and heat consumption, respectively; further, the efficiency of the high pressure cylinder, the middle pressure cylinder and the low pressure cylinder is respectively reduced by 1%, and the influence of the change of the cylinder efficiency on the heat consumption rate is analyzed.
The RBF neural network prediction algorithm comprises the following calculation steps:
in the optimization process, the immature convergence phenomenon can be effectively overcome by calculating the information entropy of each 2 individuals and adding the judgment of antibody diversity, and the convergence efficiency of the algorithm can be improved. The invention builds a mixed RBF neural network prediction algorithm by applying the algorithm, and the specific design steps are as follows:
(1) Determining the number of nodes of the input layer and the output layer according to the problem to form a central set sample;
(2) Randomly selecting a certain number of samples from the central set, wherein the corresponding input vector is used as the center of the hidden layer unit, and the number of the selected samples is used as the number of the hidden layer unit, so that an initial population is randomly generated;
(3) Evolution operations, such as operator operations of mutation, crossover, etc.;
(4) Firstly, constructing a hidden layer structure of the network by using the selected samples, then determining weights from the hidden layer to an output layer by using a gradient method, and calculating the total error of the network. If the maximum network structure is not reached, executing the step (3), otherwise executing the step (5);
(5) The fitness of each antibody is calculated, and the fitness function can be taken as:
wherein: c is a constant; e, e i Is an iteration error; f (i) is a fitness function.
(6) Concentration-based immunomodulation of antibodies, generation of new individuals, and transfer to step (3).
Wherein, the larger the antibody fitness is, the larger the selection probability is; the greater the antibody concentration, the less probability of selection. Thus, the phenomenon of immature convergence can be improved by further ensuring antibody diversity while retaining highly adaptive antibodies.
For a 660MW supercritical unit, the efficiency of the low-pressure cylinder is determined based on an RBF neural network prediction algorithm, and the enthalpy value of the steam turbine cannot be obtained by a conventional method because the 7 th section and the 8 th section of steam extraction of the steam turbine can be located in a wet steam area. Therefore, the 1 st stage of steam extraction enthalpy is predicted by utilizing the 1 st stage of RBF network to firstly fit a 1-6 stage of steam extraction point model in the superheat region;
the predicted data and the input data of the 1 st layer are used as the input data of the 2 nd RBF neural network, and the 8 th section of steam extraction enthalpy is predicted;
and (3) taking the predicted data and the input data of the layer 2 as the input data of the RBF neural network of the layer 3, and predicting the enthalpy of the exhaust steam of the final stage, so as to calculate the relative internal efficiency of the low-pressure cylinder of the steam turbine.
In actual calculation, different normalization processes are adopted for different input parameters, and the method has the following greatest advantages: the relative internal efficiency of the low-pressure cylinder under the current working condition can be dynamically obtained, and the calculation efficiency can be greatly improved.
The definition formula of the steam turbine heat consumption q is as follows:
wherein: q is the heat rate of the turbine, kJ/(kW.s); q is the heat quantity of the system, kJ/s; p is the generated power, kW.
The influence of the high-pressure cylinder efficiency change on the heat consumption is determined, the high-pressure cylinder efficiency change can lead to the internal power change of the high-pressure cylinder and the change of the heat absorption capacity of the boiler reheater, and the high-pressure cylinder efficiency change can lead to the calculation of the change of the vapor exhaust enthalpy of the high-pressure cylinder by the following formula:
wherein: δh HPE Is the change quantity of the exhaust enthalpy of the high-pressure cylinder, kJ/kg; h is a HPE And h' HPE Respectively high pressure before and after changeCylinder exhaust enthalpy, kJ/kg; Δη HP And eta HP The absolute value of the high pressure cylinder efficiency change and the high pressure cylinder efficiency, respectively.
Wherein: g RH Kg/s is the reheat flow of the boiler; r is R HP The nominal internal power of the high-pressure cylinder is the percentage of the total generated power.
If the efficiency of the high-pressure cylinder is reduced, the reduced internal power becomes a factor for increasing the heat rate, and the reduced reheat heat absorption capacity of the boiler becomes a factor for reducing the heat rate.
The effect of the change in medium pressure cylinder efficiency on heat consumption was further analyzed:
the change in the efficiency of the medium pressure cylinder will on the one hand result in a change in the internal power of the medium pressure cylinder and on the other hand also affect a change in the internal power of the low pressure cylinder. The impact of the medium pressure cylinder efficiency change on the medium pressure cylinder internal power is similar to the impact of the high pressure cylinder efficiency change on the high pressure cylinder internal power, and can be calculated by adopting a formula with a similar formula:
wherein: r is R IP The nominal internal power of the medium-pressure cylinder accounts for the percentage of the total generated power; LF is dissipation factor.
The loss factor LF is actually the loss proportion caused by the fact that the enthalpy increase such as the steam inlet of the low-pressure cylinder is not effectively utilized, and the loss factor (1-LF) is the proportion effectively utilized; r is R IP Nominal power for the medium pressure cylinder as a percentage of total power.
The effect of the change in low pressure cylinder efficiency on heat consumption was determined:
the influence of the change of the low-pressure cylinder efficiency on the heat consumption rate is as follows:
in the derivation process of the formula, the regenerative extraction of the thermodynamic system and the steam for the water pump turbine are not considered, and the steam discharge flow of each cylinder is equal to the steam inlet flow. Because the actual steam turbine has the heat recovery and steam extraction of the thermodynamic system, the steam extraction flow of each cylinder is smaller than the steam inlet flow, and a certain error is caused to the calculation result, and corresponding discussion is made here.
According to R HP 、R IP 、R LP If the calculation formula of the (2) is adopted for calculating the steam inflow of each cylinder, the calculated influence quantity is larger; the calculated influence amount is made smaller if the cylinder discharge flow rate is used for calculation.
To reduce the error, it is considered to replace with the percentage of the total electric power in the actual internal power of each cylinder. The corresponding formula is:
wherein: g HP,in The flow rate of the inlet gas of the high-pressure cylinder is kg/s; g LP,in The flow rate of the inlet gas of the high-pressure cylinder is kg/s; g IP,in The flow rate of the inlet gas of the high-pressure cylinder is kg/s; h is a HP,ext Extracting specific enthalpy of each section of the high-pressure cylinder, kJ/kg; h is a IP,ext Extracting specific enthalpy of each section of the medium pressure cylinder, kJ/kg; h is a LP,ext Extracting specific enthalpy of each section of the low-pressure cylinder, kJ/kg;
according to the invention, based on RBF neural network prediction algorithm, different normalization processes are adopted for different input parameters, according to a relative internal efficiency calculation formula, after the efficiency change eta=1% of each cylinder is calculated by the design cylinder efficiency back-calculation, the corresponding change quantity delta h of the exhaust steam enthalpy value is obtained, and because the high and medium pressure cylinders are in a overheat area due to thermal parameters, the basic parameters, the cylinder efficiency and the like can be determined through temperature and pressure. Because the steam exhaust port of the low-pressure cylinder is positioned in the two-phase region, the steam exhaust enthalpy and entropy of the low-pressure cylinder cannot be determined through parameters such as temperature, pressure and the like, the cylinder efficiency of the low-pressure cylinder is based on an RBF neural network prediction algorithm, and the steam extraction enthalpy of the 7 th section is predicted by fitting a 1-6 section steam extraction point model in the superheat region by utilizing a 1 st layer RBF network; the predicted data and the input data of the 1 st layer are used as the input data of the 2 nd RBF neural network, and the 8 th section of steam extraction enthalpy is predicted; and then, the predicted data and the input data of the 2 nd layer are used as the input data of the 3 rd layer RBF neural network, and the final steam exhaust enthalpy is predicted, so that the relative internal efficiency of the low-pressure cylinder of the steam turbine is calculated. Based on this, in the case of analyzing the low-pressure cylinder efficiency decrease by 1%, the influence of the low-pressure cylinder efficiency change on the heat rate is further determined from the above-described expression of the pushed cylinder efficiency influence on the heat rate.
Examples
Referring to fig. 1, a simplified diagram of an RBF neural network prediction algorithm model according to an embodiment of the invention includes: input sample x i Input layer, hidden layer, output layer and output y i And the like. For a certain 660MW supercritical unit, as the temperature and pressure of the steam inlet parameters of the low-pressure cylinder are relatively low, steam is extracted from seven sections, eight sections and the low-pressure cylinderThe exhaust gas may be in a two-phase region, when in which enthalpy and entropy cannot be determined by temperature and pressure. Therefore, the efficiency of the low-pressure cylinder is determined by adopting a prediction model, and the extraction enthalpy of the 7 th section is predicted by adopting an RBF neural network prediction algorithm and firstly fitting out a 1-6 section extraction point model in a superheat region by utilizing a 1 st layer RBF network; the predicted data and the input data of the 1 st layer are used as the input data of the 2 nd RBF neural network, and the 8 th section of steam extraction enthalpy is predicted; and then, the predicted data and the input data of the layer 2 are used as the input data of the RBF neural network of the layer 3, and the final steam exhaust enthalpy is predicted. When the extraction enthalpy of the 7 th section, the extraction enthalpy of the 8 th section and the final exhaust enthalpy are determined, the efficiency of the low pressure cylinder is also determined. Besides, the high and medium pressure cylinders are in the overheat area due to the fact that the steam extraction and steam discharge ports are located in the overheat area, and therefore the efficiency of the high and medium pressure cylinders can be determined through the temperature and the pressure of the test. Based on the determined cylinder efficiency, the effect of cylinder efficiency variation on heat rate is further analyzed when the high, medium and low pressure cylinder efficiency varies by 1% from the formula of heat rate of cylinder efficiency derived as described above.
Referring to fig. 2, a schematic flow chart is shown, which is a flow chart for analyzing the influence of cylinder efficiency on heat consumption. Firstly, data acquisition is carried out, acquired test data comprise temperature, pressure and flow, the acquired partial data are subjected to normalization processing, the efficiency of a low-pressure cylinder is determined through an RBF neural network prediction algorithm, however, the efficiency of the high-pressure cylinder and the medium-pressure cylinder can be directly obtained through the measured test data, further, the efficiency of the high-pressure cylinder, the efficiency of the medium-pressure cylinder and the efficiency of the low-pressure cylinder are respectively changed by 1%, and the influence of the change of the efficiency of the cylinders on the heat consumption rate is respectively analyzed.
Finally, it should be noted that: the above embodiments are only for illustrating the technical aspects of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: modifications and equivalents may be made to the specific embodiments of the invention without departing from the spirit and scope of the invention, which is intended to be covered by the claims.
Claims (7)
1. The method for calculating the influence of the cylinder efficiency change of the supercritical thermal power unit on the heat consumption rate is characterized by comprising the following steps of:
1) Collecting test data;
2) Normalizing the collected test data;
3) According to the test data after normalization treatment, determining the efficiency eta of the high-pressure cylinder HP Efficiency eta of medium pressure cylinder IP And determining the efficiency eta of the low-pressure cylinder based on RBF neural network prediction algorithm LP The method comprises the steps of carrying out a first treatment on the surface of the The cylinder efficiency of the low-pressure cylinder is based on an RBF neural network prediction algorithm, and the 1-6 sections of steam extraction point models in the superheat region are firstly fitted by utilizing the 1 st layer RBF neural network, so that the steam extraction enthalpy of the 7 th section is predicted;
the predicted data and the input data of the 1 st layer are used as the input data of the 2 nd RBF neural network, and the 8 th section of steam extraction enthalpy is predicted;
then, the predicted data and the input data of the 2 nd layer are used as the input data of the 3 rd layer RBF neural network, and the final steam exhaust enthalpy is predicted, so that the cylinder efficiency of the low-pressure cylinder of the steam turbine is calculated;
4) Respectively changing the efficiency eta of the high-pressure cylinder HP Efficiency eta of medium pressure cylinder IP And low pressure cylinder efficiency eta LP The efficiency of each cylinder is reduced by 1%;
5) And under the condition that the efficiency of each cylinder is reduced by 1%, obtaining a corresponding heat consumption rate, and comparing and analyzing to determine the influence of the heat efficiency change of each cylinder on the heat loss.
2. The method for calculating the influence of cylinder efficiency change on heat rate of supercritical thermal power generating unit according to claim 1, wherein in step 1), the test data includes temperature, pressure and flow rate of each test point.
3. The method for calculating the influence of cylinder efficiency variation of a supercritical thermal power generating unit on a heat consumption rate according to claim 1, wherein the calculating step of the RBF neural network prediction algorithm comprises:
(1) Determining the number of nodes of the input layer and the output layer according to the problem to form a central set sample;
(2) Randomly selecting a predetermined number of samples from the central set, wherein the corresponding input vector is used as the center of the hidden layer unit, and the number of the selected samples is used as the number of the hidden layer unit, so that an initial population is randomly generated;
(3) Evolution operations, including mutation and crossover operator operations;
(4) Firstly constructing a hidden layer structure of a network by using a selected sample, determining weights from the hidden layer to an output layer by using a gradient method, calculating total errors of the network, and executing the step (3) if the total errors of the network do not reach the maximum network structure which is originally set, otherwise, executing the step (5);
(5) The fitness of each antibody was calculated and the fitness function was taken as:
wherein: c is a constant; e, e i Is an iteration error; f (i) is an fitness function;
(6) Performing concentration-based immunomodulation on the antibodies, generating new individuals, and transferring to step (3); wherein, the larger the antibody fitness is, the larger the selection probability is; the greater the antibody concentration, the less the probability of selection; the phenomenon of immature convergence can be improved by further ensuring the diversity of the antibody while retaining the antibody with high adaptability.
4. The method for calculating the influence of the cylinder efficiency change of the supercritical thermal power generating unit on the heat consumption rate according to claim 1, wherein the influence of the cylinder efficiency change on the heat consumption is deduced, the cylinder efficiency change causes the internal power change of the cylinder and the heat absorption capacity change of the boiler reheater, and the cylinder efficiency change causes the vapor discharge enthalpy change of the cylinder to be calculated by the following formula:
wherein: δh HPE Is a high-pressure cylinder rowVariation of vapor enthalpy, kJ/kg; h is a HPE And h' HPE The enthalpy of exhaust gas of the high-pressure cylinder before and after the change is kJ/kg; Δη HP And eta HP The absolute value of the high-pressure cylinder efficiency change and the high-pressure cylinder efficiency are respectively;
wherein: g RH Kg/s is the reheat flow of the boiler; r is R HP The nominal internal power of the high-pressure cylinder accounts for the percentage of the total power generation power, q is the heat consumption rate of the turbine, kJ/(kW.s); Δq is the variation of the heat rate of the steam turbine, kJ/(kW.s); p is the generated power, kW.
5. The method for calculating the influence of cylinder efficiency change of a supercritical thermal power generating unit on a heat consumption rate according to claim 4, wherein a definition formula of a heat consumption rate q of a steam turbine is as follows:
wherein: q is the heat quantity, kJ/s.
6. The method for calculating the influence of the cylinder efficiency change of the supercritical thermal power generating unit on the heat consumption rate according to claim 1, wherein the influence of the medium pressure cylinder efficiency change on the heat consumption rate is deduced, and the medium pressure cylinder efficiency change leads to the inner power change of the medium pressure cylinder on one hand and affects the inner power change of the low pressure cylinder on the other hand; the medium pressure cylinder efficiency variation is calculated using the following formula:
wherein: r is R IP The nominal internal power of the medium-pressure cylinder accounts for the percentage of the total generated power; LF is dissipation factor;
the loss factor LF is actually the loss ratio caused by the fact that the enthalpy such as the admission of the low-pressure cylinder is not effectively utilized, and (1-LF) is the ratio effectively utilized.
7. The method for calculating the influence of the cylinder efficiency change of the supercritical thermal power generating unit on the heat consumption rate according to claim 1, wherein the influence of the low-pressure cylinder efficiency change on the heat consumption rate is deduced, and the influence of the low-pressure cylinder efficiency change on the heat consumption rate is:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210706730.8A CN115099029B (en) | 2022-06-21 | 2022-06-21 | Method for calculating influence of cylinder efficiency change of supercritical thermal power generating unit on heat consumption rate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210706730.8A CN115099029B (en) | 2022-06-21 | 2022-06-21 | Method for calculating influence of cylinder efficiency change of supercritical thermal power generating unit on heat consumption rate |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115099029A CN115099029A (en) | 2022-09-23 |
| CN115099029B true CN115099029B (en) | 2024-03-12 |
Family
ID=83293755
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210706730.8A Active CN115099029B (en) | 2022-06-21 | 2022-06-21 | Method for calculating influence of cylinder efficiency change of supercritical thermal power generating unit on heat consumption rate |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115099029B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102680144A (en) * | 2012-05-21 | 2012-09-19 | 东南大学 | Method for measuring influence of steam leakage rates of middle separation shaft seal of turbine on unit heat consumption rate |
| CN107201921A (en) * | 2017-03-10 | 2017-09-26 | 国电科学技术研究院 | A kind of thermal loss of steam turbine rate on-line monitoring system and measuring method |
| CN110032791A (en) * | 2019-04-08 | 2019-07-19 | 西安热工研究院有限公司 | Turbine low pressure cylinder efficiency real-time computing technique based on generalized regression nerve networks |
| CN111664504A (en) * | 2020-06-11 | 2020-09-15 | 上海明华电力科技有限公司 | Method for predicting influence of turbine thermodynamic system micro-increment variable on turbine heat consumption |
| CN113486472A (en) * | 2021-07-26 | 2021-10-08 | 国能南京电力试验研究有限公司 | Method for calculating influence quantity of steam turbine cylinder efficiency on heat rate |
| CN113902326A (en) * | 2021-10-21 | 2022-01-07 | 上海电机学院 | Biomass unit electric energy quality and unit efficiency measurement and control system based on FPGA |
| CN114239218A (en) * | 2021-11-09 | 2022-03-25 | 中国大唐集团科学技术研究院有限公司中南电力试验研究院 | Optimization calculation method for main steam pressure of steam turbine set under variable working conditions |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2020067762A (en) * | 2018-10-23 | 2020-04-30 | トヨタ自動車株式会社 | Control assisting device, apparatus controller, control assisting method, control assisting program, prelearned model for making computer function, and method for generating prelearned model |
-
2022
- 2022-06-21 CN CN202210706730.8A patent/CN115099029B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102680144A (en) * | 2012-05-21 | 2012-09-19 | 东南大学 | Method for measuring influence of steam leakage rates of middle separation shaft seal of turbine on unit heat consumption rate |
| CN107201921A (en) * | 2017-03-10 | 2017-09-26 | 国电科学技术研究院 | A kind of thermal loss of steam turbine rate on-line monitoring system and measuring method |
| CN110032791A (en) * | 2019-04-08 | 2019-07-19 | 西安热工研究院有限公司 | Turbine low pressure cylinder efficiency real-time computing technique based on generalized regression nerve networks |
| CN111664504A (en) * | 2020-06-11 | 2020-09-15 | 上海明华电力科技有限公司 | Method for predicting influence of turbine thermodynamic system micro-increment variable on turbine heat consumption |
| CN113486472A (en) * | 2021-07-26 | 2021-10-08 | 国能南京电力试验研究有限公司 | Method for calculating influence quantity of steam turbine cylinder efficiency on heat rate |
| CN113902326A (en) * | 2021-10-21 | 2022-01-07 | 上海电机学院 | Biomass unit electric energy quality and unit efficiency measurement and control system based on FPGA |
| CN114239218A (en) * | 2021-11-09 | 2022-03-25 | 中国大唐集团科学技术研究院有限公司中南电力试验研究院 | Optimization calculation method for main steam pressure of steam turbine set under variable working conditions |
Non-Patent Citations (1)
| Title |
|---|
| 汽轮机缸相对效率变化对热耗影响的计算方法;万忠海;闻敏;;江西电力(第03期);第25-27页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115099029A (en) | 2022-09-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108446529B (en) | Organic Rankine cycle system fault detection method based on generalized mutual entropy-DPCA algorithm | |
| CN106682376B (en) | Whole-process steam turbine modeling and identification method for actual characteristics of parameters changing along with working conditions | |
| CN109211439B (en) | Steam turbine low-pressure cylinder exhaust steam enthalpy value online monitoring system and method | |
| CN109388844B (en) | Correction calculation method for energy-saving effect of low-pressure economizer | |
| CN107368680A (en) | A kind of steam turbine optimum vacuum real-time computing technique | |
| CN111652418B (en) | Method for generating sliding pressure curve of dynamic refined composite parameter of thermal power generating unit | |
| CN107908865A (en) | A kind of exhaust enthalpy of low pressure cylinder of steam turbine real-time computing technique based on machine algorithm | |
| CN115510904B (en) | Boiler heating area ash monitoring method based on time sequence prediction | |
| CN111581821A (en) | Heat supply unit peak regulation capacity determination method based on measured performance parameters | |
| CN111142381B (en) | Control-oriented NCB type steam turbine heating system composite dynamic modeling method | |
| CN111664504A (en) | Method for predicting influence of turbine thermodynamic system micro-increment variable on turbine heat consumption | |
| CN114757269A (en) | Complex process refined fault detection method based on local subspace-neighborhood preserving embedding | |
| CN115099029B (en) | Method for calculating influence of cylinder efficiency change of supercritical thermal power generating unit on heat consumption rate | |
| CN112127957B (en) | Method for measuring main steam flow of steam turbine of thermal power plant | |
| CN112231908B (en) | Method for determining upper and lower load limits corresponding to extraction flow of extraction condensing unit | |
| CN113486472A (en) | Method for calculating influence quantity of steam turbine cylinder efficiency on heat rate | |
| CN104459542A (en) | Heat rate measurement method for reheating regeneration combined cycle unit | |
| JPWO2005041209A1 (en) | Nuclear power plant thermal efficiency diagnostic system, nuclear power plant thermal efficiency diagnostic program, and nuclear power plant thermal efficiency diagnostic method | |
| CN111737859B (en) | Improved turbine unit variable-pressure operation consumption difference quantitative calculation model construction method | |
| CN110032791B (en) | Turbine low-pressure cylinder efficiency real-time calculation method based on generalized regression neural network | |
| CN109655275B (en) | Gas turbine cycle heat economy diagnosis method based on sensitivity coefficient method | |
| CN112100751A (en) | Method and system for calculating influence of backpressure change of extraction and coagulation unit on unit power | |
| CN114856726B (en) | Real-time determination method for exhaust steam volume flow and humidity of saturated steam turbine | |
| CN104537226B (en) | Backheat work done ratio and backheat ratio of profit increase assay method when reheating embrittlement has hydrophobic cold source energy | |
| CN113158444B (en) | Correction calculation method for influence of low-temperature economizer operation on steam turbine heat consumption |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |